Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /download
    -0.07
     trabalho
    -0.07
    /Open
    -0.06
     Montgomery
    -0.06
    insert
    -0.06
    Notifications
    -0.06
    flake
    -0.06
    widget
    -0.06
    EATURE
    -0.06
     Harris
    -0.06
    POSITIVE LOGITS
    _pred
    0.07
    انون
    0.07
    医院
    0.07
    ουν
    0.06
    -yyyy
    0.06
     aiding
    0.06
    제
    0.06
    敢
    0.06
    ,Yes
    0.06
     Hab
    0.06
    Act Density 0.115%

    No Known Activations